Merge pull request #103 from ucl-cssb/improve-bayes-gLV-examples

Improve bayes g lv examples

Author: Fontanapink

examples/gLV/examples-Rutter-Dekker.ipynb

@@ -247,7 +247,7 @@
     }
    ],
    "source": [
-    "# read in pickled simulated parameters, mu, M, epsilon\n",
+    "# read in pickled simulated parameters, mu, M, epsilon, created in examples-sim-gLV.ipynb\n",
     "num_species = 5\n",
     "with open(\"params-s5.pkl\", \"rb\") as f:\n",
     "    params = pickle.load(f)\n",
@@ -818,20 +818,6 @@
     "#inference.plot_posterior(idata)\n",
     "\n",
     "\n",
-    "\n",
-    "\n",
-    "#nX = num_species\n",
-    "#n_obs = times.shape[0] - 1\n",
-    "#noise_stddev = 0.1\n",
-    "\n",
-    "# Params for shrinkage on M_ij (non diagonal elements)\n",
-    "#DA = nX*nX - nX\n",
-    "#DA0 = 3     # expected number of non zero entries in M_ij\n",
-    "#N = n_obs - 2\n",
-    "\n",
-    "#inference = infergLVbayes(X, F, mu_prior, M_prior, DA=DA, DA0=DA0, N=N, noise_stddev=noise_stddev)\n",
-    "#idata = inference.run_bayes_gLV_shrinkage()\n",
-    "\n",
     "# print summary\n",
     "summary = az.summary(idata, var_names=[\"mu_hat\", \"M_ii_hat\", \"M_ij_hat\", \"M_hat\", \"sigma\"])\n",
     "print(summary[[\"mean\", \"sd\", \"r_hat\"]])\n",
@@ -862,7 +848,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "c6d6c2df",
    "metadata": {
     "ExecuteTime": {
@@ -1108,20 +1094,6 @@
     "#inference.plot_posterior_pert(idata)\n",
     "\n",
     "\n",
-    "\n",
-    "\n",
-    "#nX = num_species\n",
-    "#n_obs = times.shape[0] - 1\n",
-    "#noise_stddev = 0.1\n",
-    "\n",
-    "# Params for shrinkage on M_ij (non diagonal elements)\n",
-    "#DA = nX*nX - nX\n",
-    "#DA0 = 3     # expected number of non zero entries in M_ij\n",
-    "#N = n_obs - 2\n",
-    "\n",
-    "#inference = infergLVbayes(X, F, mu_prior, M_prior, DA=DA, DA0=DA0, N=N, noise_stddev=noise_stddev, epsilon=epsilon)\n",
-    "#idata = inference.run_bayes_gLV_shrinkage_pert()\n",
-    "\n",
     "# print summary\n",
     "summary = az.summary(idata, var_names=[\"mu_hat\", \"M_ii_hat\", \"M_ij_hat\", \"M_hat\", \"epsilon_hat\", \"sigma\"])\n",
     "print(summary[[\"mean\", \"sd\", \"r_hat\"]])\n",

examples/gLV/examples-bayes-gLV.ipynb

@@ -279,7 +279,7 @@ def _run_inference_large(self, **kwargs) -> None:
             c2 = pm.InverseGamma("c2", 2, 8)
             tau = pm.HalfCauchy("tau", beta=tau0)
             lam = pm.HalfCauchy("lam", beta=1, shape=(ndim, ndim))
-            A = pm.Normal('A', mu=A_prior_mu, sigma=tau * lam * \
+            A = pm.Normal('A', mu=A_prior_mu, sigma=tau * lam *
                           at.sqrt(c2 / (c2 + tau**2 * lam**2)), shape=(ndim, ndim))
 
             # If noise covariance is provided, use it as a prior
@@ -438,14 +438,14 @@ def _run_inference_large_xs(self, **kwargs) -> None:
             c2_A = pm.InverseGamma("c2_A", 2, 1)
             tau_A = pm.HalfCauchy("tau_A", beta=tau0_A)
             lam_A = pm.HalfCauchy("lam_A", beta=1, shape=(nX, nX))
-            Ah = pm.Normal('Ah', mu=A_prior_mu, sigma=tau_A * lam_A * \
+            Ah = pm.Normal('Ah', mu=A_prior_mu, sigma=tau_A * lam_A *
                            at.sqrt(c2_A / (c2_A + tau_A**2 * lam_A**2)), shape=(nX, nX))
 
             tau0_B = (DB0 / (DB - DB0)) * 0.1 / np.sqrt(N)
             c2_B = pm.InverseGamma("c2_B", 2, 1)
             tau_B = pm.HalfCauchy("tau_B", beta=tau0_B)
             lam_B = pm.HalfCauchy("lam_B", beta=1, shape=(nS, nX))
-            Bh = pm.Normal('Bh', mu=0, sigma=tau_B * lam_B * \
+            Bh = pm.Normal('Bh', mu=0, sigma=tau_B * lam_B *
                            at.sqrt(c2_B / (c2_B + tau_B**2 * lam_B**2)), shape=(nS, nX))
 
             if noise_cov_prior is not None:

mimic/model_infer/infer_VAR_bayes.py

@@ -9,12 +9,18 @@
 
 
 def plot_gLV(yobs, timepoints):
-    # fig, axs = plt.subplots(1, 2, layout='constrained')
+    # fig, axs = plt.subplots(1, 2, layout='constrained')  # Optional
+    # alternative
     fig, axs = plt.subplots(1, 1)
     for species_idx in range(yobs.shape[1]):
-        axs.plot(timepoints, yobs[:, species_idx], color=cols[species_idx])
+        label = f'Species {species_idx + 1}'  # Add a label for each species
+        axs.plot(timepoints, yobs[:, species_idx],
+                 color=cols[species_idx], label=label)
+
     axs.set_xlabel('time')
     axs.set_ylabel('[species]')
+    axs.legend()  # Ensure the legend is called on the correct axes
+    plt.show()
 
 
 def plot_gMLV(yobs, sobs, timepoints):